{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ONZNUBPN2KBNEUEI3F6PTVUCFG","short_pith_number":"pith:ONZNUBPN","schema_version":"1.0","canonical_sha256":"7372da05edd282d25088d97cf9d68229b7af1502da0f686f983d9f367ad94858","source":{"kind":"arxiv","id":"2305.15387","version":1},"attestation_state":"computed","paper":{"title":"Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Avi Caciularu, Ido Dagan, Jacob Goldberger, Matthew E. Peters","submitted_at":"2023-05-24T17:48:40Z","abstract_excerpt":"The integration of multi-document pre-training objectives into language models has resulted in remarkable improvements in multi-document downstream tasks. In this work, we propose extending this idea by pre-training a generic multi-document model from a novel cross-document question answering pre-training objective. To that end, given a set (or cluster) of topically-related documents, we systematically generate semantically-oriented questions from a salient sentence in one document and challenge the model, during pre-training, to answer these questions while \"peeking\" into other topically-rela"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.15387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T17:48:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9e59a86663cce4853081b921fa54d25990cc74b56f7a246dbd51942b9b8fcafc","abstract_canon_sha256":"976f24641bd98fb851b7ed70fc1de3da078db5f2cd0c9ae305f1c6c0130a80b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:34.648213Z","signature_b64":"qSZ3THsUU8xVI0PxGuwRvG/oJVYa7Sx3bG93F2P+XAKvhwaK/Ndn+hcqoqzc1gq0C3S/sQ6EkhiJ9Gmq685sDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7372da05edd282d25088d97cf9d68229b7af1502da0f686f983d9f367ad94858","last_reissued_at":"2026-07-05T06:13:34.647860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:34.647860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Avi Caciularu, Ido Dagan, Jacob Goldberger, Matthew E. Peters","submitted_at":"2023-05-24T17:48:40Z","abstract_excerpt":"The integration of multi-document pre-training objectives into language models has resulted in remarkable improvements in multi-document downstream tasks. In this work, we propose extending this idea by pre-training a generic multi-document model from a novel cross-document question answering pre-training objective. To that end, given a set (or cluster) of topically-related documents, we systematically generate semantically-oriented questions from a salient sentence in one document and challenge the model, during pre-training, to answer these questions while \"peeking\" into other topically-rela"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15387","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.15387/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.15387","created_at":"2026-07-05T06:13:34.647923+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15387v1","created_at":"2026-07-05T06:13:34.647923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15387","created_at":"2026-07-05T06:13:34.647923+00:00"},{"alias_kind":"pith_short_12","alias_value":"ONZNUBPN2KBN","created_at":"2026-07-05T06:13:34.647923+00:00"},{"alias_kind":"pith_short_16","alias_value":"ONZNUBPN2KBNEUEI","created_at":"2026-07-05T06:13:34.647923+00:00"},{"alias_kind":"pith_short_8","alias_value":"ONZNUBPN","created_at":"2026-07-05T06:13:34.647923+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.18830","citing_title":"MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ONZNUBPN2KBNEUEI3F6PTVUCFG","json":"https://pith.science/pith/ONZNUBPN2KBNEUEI3F6PTVUCFG.json","graph_json":"https://pith.science/api/pith-number/ONZNUBPN2KBNEUEI3F6PTVUCFG/graph.json","events_json":"https://pith.science/api/pith-number/ONZNUBPN2KBNEUEI3F6PTVUCFG/events.json","paper":"https://pith.science/paper/ONZNUBPN"},"agent_actions":{"view_html":"https://pith.science/pith/ONZNUBPN2KBNEUEI3F6PTVUCFG","download_json":"https://pith.science/pith/ONZNUBPN2KBNEUEI3F6PTVUCFG.json","view_paper":"https://pith.science/paper/ONZNUBPN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15387&json=true","fetch_graph":"https://pith.science/api/pith-number/ONZNUBPN2KBNEUEI3F6PTVUCFG/graph.json","fetch_events":"https://pith.science/api/pith-number/ONZNUBPN2KBNEUEI3F6PTVUCFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ONZNUBPN2KBNEUEI3F6PTVUCFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ONZNUBPN2KBNEUEI3F6PTVUCFG/action/storage_attestation","attest_author":"https://pith.science/pith/ONZNUBPN2KBNEUEI3F6PTVUCFG/action/author_attestation","sign_citation":"https://pith.science/pith/ONZNUBPN2KBNEUEI3F6PTVUCFG/action/citation_signature","submit_replication":"https://pith.science/pith/ONZNUBPN2KBNEUEI3F6PTVUCFG/action/replication_record"}},"created_at":"2026-07-05T06:13:34.647923+00:00","updated_at":"2026-07-05T06:13:34.647923+00:00"}